Qichun Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qichun Wu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Dingwen Bai
Business School, Chengdu University of Technology, Chengdu 610059, China
1 shared publication - MuGa WaEr
Business School, Chengdu University of Technology, Chengdu 610059, China
1 shared publication - Yan Ke
China E-Commerce Association Innovation & Integration Information Technology Research Institute, Beijing 100037, China
1 shared publication - Yang Qiu
China E-Commerce Association Innovation & Integration Information Technology Research Institute, Beijing 100037, China
1 shared publication - Zilong Hou
China E-Commerce Association Innovation & Integration Information Technology Research Institute, Beijing 100037, China
1 shared publication - Ziyang Liu
Asian Business Research Institute, Hong Kong, China
1 shared publication
Latest Publications
- Open Access
- 17 March 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (6) , 1012
FedQuAD: Fast-Converging Curvature-Aware Federated Learning for Credit Default Prediction from Private Accounting Data
Credit default prediction from firm-level accounting statements is central to risk management, yet the underlying financial data are highly sensitive and often siloed across banks, auditors, and platforms. Federated learning (FL) offers a practical route to collaborative modeling without centralizing raw records, but standard FL optimization can converge slowly under severe client heterogeneity, heavy-tailed accounting features, and label imbalance typical of default events. This paper proposes FedQuAD, a novel fast-converging FL algorithm that couples (i) quasi-Newton curvature aggregation on the server with a lightweight limited-memory update to accelerate global progress, (ii) a proximal variance-reduced local solver that stabilizes client drift under non-IID accounting distributions, and (iii) federated robust standardization of tabular financial ratios via secure aggregated quantile statistics to mitigate scale instability and outliers. FedQuAD is communication-efficient by design: It transmits compact gradient and curvature sketches and adapts local computation to each client’s stochasticity and drift. We provide convergence guarantees for strongly convex default-risk objectives (logistic and calibrated GLM losses) under bounded heterogeneity, and extend the analysis to nonconvex deep tabular models via expected stationarity bounds. Experiments on public credit-risk benchmarks with simulated cross-silo (institutional) partitions demonstrate that FedQuAD reaches target AUC and calibration error with substantially fewer communication rounds than representative baselines while maintaining privacy constraints compatible with secure aggregation and optional client-level differential privacy accounting.
- 17 March 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (6) , 1012
Open AccessFedQuAD: Fast-Converging Curvature-Aware Federated Learning for Credit Default Prediction from Private Accounting Data
Credit default prediction from firm-level accounting statements is central to risk management, yet the underlying financial data are highly sensitive and often siloed across banks, auditors, and platforms. Federated learning (FL) offers a practical route to collaborative modeling without centralizing raw records, but standard FL optimization can converge slowly under severe client heterogeneity, heavy-tailed accounting features, and label imbalance typical of default events. This paper proposes FedQuAD, a novel fast-converging FL algorithm that couples (i) quasi-Newton curvature aggregation on the server with a lightweight limited-memory update to accelerate global progress, (ii) a proximal variance-reduced local solver that stabilizes client drift under non-IID accounting distributions, and (iii) federated robust standardization of tabular financial ratios via secure aggregated quantile statistics to mitigate scale instability and outliers. FedQuAD is communication-efficient by design: It transmits compact gradient and curvature sketches and adapts local computation to each client’s stochasticity and drift. We provide convergence guarantees for strongly convex default-risk objectives (logistic and calibrated GLM losses) under bounded heterogeneity, and extend the analysis to nonconvex deep tabular models via expected stationarity bounds. Experiments on public credit-risk benchmarks with simulated cross-silo (institutional) partitions demonstrate that FedQuAD reaches target AUC and calibration error with substantially fewer communication rounds than representative baselines while maintaining privacy constraints compatible with secure aggregation and optional client-level differential privacy accounting.
- Open Access
- 12 November 2025
- Published by MDPI AG in Electronics
- Vol. 14 (22) , 4405
Fast-Converging and Trustworthy Federated Learning Framework for Privacy-Preserving Stock Price Modeling
Stock price modeling under privacy constraints presents a unique challenge at the intersection of computational economics and machine learning. Financial institutions and brokerage firms hold valuable yet sensitive data that cannot be centrally aggregated due to privacy laws and competitive concerns. To address this issue, we propose a novel Fast-Converging Federated Learning (FCFL) framework that enables decentralized and privacy-preserving stock price modeling. FCFL employs a dual-stage adaptive optimization strategy that dynamically tunes local learning rates and aggregation weights based on inter-client gradient divergence, accelerating convergence in heterogeneous financial environments. The framework integrates secure aggregation and differential privacy mechanisms to prevent information leakage during communication while maintaining model fidelity. Experimental results on multi-institutional stock datasets demonstrate that FCFL achieves up to 30% faster convergence and 2.5% lower prediction error compared to conventional federated averaging approaches, while guaranteeing strong -differential privacy. Theoretical analysis further proves that the framework attains sublinear convergence in communication rounds under non-IID data distributions. This study provides a new direction for collaborative financial modeling, balancing efficiency, accuracy, and privacy in real-world economic systems.- 12 November 2025
- Published by MDPI AG in Electronics
- Vol. 14 (22) , 4405
Open AccessFast-Converging and Trustworthy Federated Learning Framework for Privacy-Preserving Stock Price Modeling
Stock price modeling under privacy constraints presents a unique challenge at the intersection of computational economics and machine learning. Financial institutions and brokerage firms hold valuable yet sensitive data that cannot be centrally aggregated due to privacy laws and competitive concerns. To address this issue, we propose a novel Fast-Converging Federated Learning (FCFL) framework that enables decentralized and privacy-preserving stock price modeling. FCFL employs a dual-stage adaptive optimization strategy that dynamically tunes local learning rates and aggregation weights based on inter-client gradient divergence, accelerating convergence in heterogeneous financial environments. The framework integrates secure aggregation and differential privacy mechanisms to prevent information leakage during communication while maintaining model fidelity. Experimental results on multi-institutional stock datasets demonstrate that FCFL achieves up to 30% faster convergence and 2.5% lower prediction error compared to conventional federated averaging approaches, while guaranteeing strong -differential privacy. Theoretical analysis further proves that the framework attains sublinear convergence in communication rounds under non-IID data distributions. This study provides a new direction for collaborative financial modeling, balancing efficiency, accuracy, and privacy in real-world economic systems.